daBongo LMS AI Training Courses

← Back to Course

Getting Started with Model Context Protocol

Lesson 1: What MCP Is and Why It Matters

Lesson Objectives

By the end of this lesson, students should be able to:

  • Explain the integration problem MCP solves
  • Describe MCP's position as an open standard vs. proprietary integration
  • Distinguish MCP tool use from Anthropic API tool use
  • Identify use cases where MCP is the right choice vs. simpler alternatives

Lesson Content

The integration problem before MCP.

Before a standardized protocol, connecting an AI model to external tools required a custom integration for every tool-model pair. Connecting Claude to a GitHub repository, a Postgres database, and a Slack workspace required three separate custom integrations – each maintaining its own authentication, schema, and update path. N models × M tools = N×M custom integrations.

What MCP standardizes.

MCP defines a common interface between AI models (clients) and external tools (servers). A tool built as an MCP server connects to any MCP-compliant AI client using the same protocol – once. The N×M problem becomes N+M: build one MCP server per tool, build one MCP client per model.

MCP vs. Anthropic API tool use.

The Anthropic API's tool use mechanism (function calling) is a model-level feature – your application defines tools in the API request and executes them directly. MCP is a separate server process running alongside your application, exposing capabilities to any connected client via the standard protocol.

When to use API tool use:

  • Simple function calls your application already executes
  • Tight integration with application logic
  • No need for cross-client reuse

When to use MCP:

  • Capabilities that should be reusable across multiple Claude applications or models
  • Complex tool implementations that benefit from a standalone server
  • Exposing organizational capabilities to multiple AI integrations

The MCP ecosystem.

MCP has a growing ecosystem of pre-built servers (file system, Git, Postgres, Slack, GitHub, and many more – verify current ecosystem at modelcontextprotocol.io). Before building a custom server, check whether a maintained pre-built server exists for your use case.

Practical Example

A developer team has three internal Claude applications that all need to query the same internal database.

Without MCP: each application implements its own database query logic.

With MCP: a single MCP server wraps the database; all three applications connect to it as an MCP client.

The database query logic is written once, maintained in one place, and updated once when the schema changes.

MCP converted a three-integration maintenance burden into one.

Safety Notes

MCP servers execute real code with real access to the resources they expose. A file system MCP server has file system access; a database MCP server has database access. The scope of permissions granted to an MCP server should match the principle of least privilege – only the access the server's legitimate functions require. Verify current MCP security guidance at modelcontextprotocol.io/security.

Log in and enroll to access lesson quizzes.

← Back to Course

Scroll to Top